Synthetic Identity Fraud: The $23B Threat Hiding in Plain Sight

What is synthetic identity fraud? 

Synthetic identity fraud is one of the fastest-growing threats to the banking industry as fraudsters slip past traditional verification methods at an alarming rate. It’s estimated that 80% of all new account fraud can be attributed to synthetic identity fraud—a number that could even be underreported thanks to how difficult synthetic fraud is to catch. 

Synthetic ID fraud is built on just enough real personally identifiable information (PII) to pass traditional authentication checks. It involves fabricating identities by combining PII such as Social Security numbers (SSNs), addresses, and birthdates from multiple people into one synthetic persona or by taking real details from a single person and mixing them with fake information. 

Fraudsters then open bank accounts, take out loans, and apply for credit cards without setting off the usual fraud red flags. By the time the damage is done, the banks are left to clean up the mess and often are responsible for the losses. 

Why is synthetic fraud so hard to detect? 

Unlike traditional identity theft, there’s no real victim to report the fraud, allowing these identities to remain active for months or even years. Synthetic fraudsters play the long game, nurturing their fake personas over time and establishing creditworthiness by making small, timely payments. They can blend in as real customers until they suddenly cash out and disappear. 

Adding to the challenge, synthetic identities are built using components of real data. Fraudsters often steal SSNs from people who aren’t monitoring their credit closely, such as children, the elderly, or the deceased. Detection became even more difficult with SSN randomization in 2011. This eliminated geographical and chronological patterns, removing a tool that banks once relied on to flag suspicious identities. 

Banks need more than static identity checks to stop synthetic fraud 

The best defense against synthetic fraud is preventing fake identities from entering the system entirely. And with synthetic losses projected to hit US $23 billion by 2030, banks that fail to adapt will continue losing millions to criminals who never should have been approved in the first place. 

Banks can’t fight today’s fraud with yesterday’s tools and expect to win. That means no longer relying exclusively on static data like credit bureau checks, which leave major gaps as fraudsters evolve. To keep synthetic fraudsters out, banks need to rethink identity verification, starting with three critical priorities.  

1. Leverage comprehensive data and real-time insights

Leveraging diverse data sources allows banks to obtain a comprehensive view of each individual and improve detection of synthetic identities. Essential data points include digital, transactional, behavioral, device-related, geospatial, and historical fraud data, all of which help create a more accurate identity profile.  

But data alone isn’t enough. It must be processed in real time through a continuous learning system that keeps banks ahead of fraudsters’ constantly evolving techniques. The faster technology can analyze identity signals, the better banks can flag bad actors before they get into their system.  

2. Include first- and third-party signals query signals

Real-time learning engines with first- and third-party signals are essential for detecting and preventing synthetic fraud in high-demand verification processes. Banks need to analyze when and where an identity first appeared, tracking first-seen and last-seen timestamps. Monitoring activity frequency and behavioral patterns helps banks identify anomalies early for proactive detection and mitigation.  

3. Take a wholistic approach to identity verification

Having data access alone isn’t enough. Banks need dynamic and diverse data to make meaningful connections between all the identity signals and detect synthetic fraud. That means verification systems must go beyond isolated, static data points and take a wholistic approach to assessing risk. 

The most successful detection systems collect and analyze identity fragments and metadata across multiple sources, labeling people, places, and behaviors to build a more complete picture. By fusing identity fragments across multiple modalities and linking identities to other entities, banks can uncover hidden connections and inconsistencies and flag more synthetic fraudsters.  

Getting ahead of synthetic ID fraud  

Banks need verification solutions that stop synthetic fraudsters at the gate. They also need those solutions to continually adapt to new risk environments. Fideo empowers banks to distinguish between real and synthetic identities. We flag suspicious activity before fraudulent relationships begin, strengthening the real-time verification process to distinguish between legitimate and high-risk users. 

How does Fideo stop synthetic ID fraud?   

Fideo leverages the most diverse data set available: 38 billion data identifiers and 3.2 billion known identities from public, private, and deep web data, financial institutions, eCommerce, call centers, web events, device/app usage, and human intelligence. 

We link trillions of signals to uncover patterns and anomalies, flagging them for escalation in real time using the bank’s existing experience and data collection. And unlike traditional providers who use static data, Fideo’s continuous update cycles run 24/7 to keep data fresh for better performance.  

Fraudsters adapt. Your bank should, too. 

Keeping synthetic fraudsters out of banks’ systems is essential to protecting a bank’s bottom line, reputation, and customer trust. Stopping synthetic fraud through superior onboarding can save millions and strengthen the integrity of each institution. 

Request a demo today to learn more about how Fideo can support your bank.